;;; mule.el --- basic commands for multilingual environment
-;; Copyright (C) 1997-2013 Free Software Foundation, Inc.
+;; Copyright (C) 1997-2014 Free Software Foundation, Inc.
;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
;; 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; because that makes a bootstrapping problem
;; if you need to recompile all the Lisp files using interpreted code.
-(defun charset-id (charset)
+(defun charset-id (_charset)
"Always return 0. This is provided for backward compatibility."
(declare (obsolete nil "23.1"))
0)
-(defmacro charset-bytes (charset)
+(defmacro charset-bytes (_charset)
"Always return 0. This is provided for backward compatibility."
(declare (obsolete nil "23.1"))
0)
;;; CHARACTER
(define-obsolete-function-alias 'char-valid-p 'characterp "23.1")
-(defun generic-char-p (char)
+(defun generic-char-p (_char)
"Always return nil. This is provided for backward compatibility."
(declare (obsolete nil "23.1"))
nil)
composition
euc-tw-shift
use-roman
- use-oldjis)
+ use-oldjis
+ 8-bit-level-4)
"List of symbols that control ISO-2022 encoder/decoder.
The value of the `:flags' attribute in the argument of the function
on decoding, and use locking-shift to invoke a graphic element on
encoding.
-If `single-shift' is specified, decode single-shift code correctly on
-decoding, and use single-shift to invoke a graphic element on encoding.
+If `single-shift' is specified, decode single-shift code
+correctly on decoding, and use single-shift to invoke a graphic
+element on encoding. See also `8-bit-level-4' specification.
If `designation' is specified, decode designation code correctly on
decoding, and use designation to designate a charset to a graphic
of ASCII.
If `use-oldjis' is specified, JIS0208-1976 is designated instead of
-JIS0208-1983.")
+JIS0208-1983.
+
+If `8-bit-level-4' is specified, the decoder assumes the
+implementation level \"4\" for 8-bit codes which means that GL is
+identified as the single-shift area. The default implementation
+level for 8-bit code is \"4A\" which means that GR is identified
+as the single-shift area.")
(defun define-coding-system (name docstring &rest props)
"Define NAME (a symbol) as a coding system with DOCSTRING and attributes.
The remaining arguments must come in pairs ATTRIBUTE VALUE. ATTRIBUTE
may be any symbol.
+A coding system specifies a rule to decode (i.e. to convert a
+byte sequence to a character sequence) and a rule to encode (the
+opposite of decoding).
+
+The decoding is done by at most 3 steps; the first is to convert
+a byte sequence to a character sequence by one of Emacs'
+internal routines specified by :coding-type attribute. The
+optional second step is to convert the character sequence (the
+result of the first step) by a translation table specified
+by :decode-translation-table attribute. The optional third step
+is to convert the above reslut by a Lisp function specified
+by :post-read-conversion attribute.
+
+The encoding is done by at most 3 steps which are reverse of the
+decoding steps. The optional first step converts a character
+sequence to another character sequence by a Lisp function
+specified by :pre-write-conversion attribute. The optional
+second step converts the above result by a translation table
+specified by :encode-translation-table attribute.. The third
+step converts the abobe result to a byte sequence by one of
+Emacs' internal routines specified by :coding-type attribute.
+
The following attributes have special meanings. Those labeled as
\"(required)\" should not be omitted.
`:coding-type' (required)
-VALUE must be one of `charset', `utf-8', `utf-16', `iso-2022',
-`emacs-mule', `shift-jis', `ccl', `raw-text', `undecided'.
+VALUE specifies the format of byte sequence the coding system
+decodes and encodes to. It must be one of `charset', `utf-8',
+`utf-16', `iso-2022', `emacs-mule', `shift-jis', `ccl',
+`raw-text', `undecided'.
+
+If VALUE is `charset', the coding system is for handling a byte
+sequence in which each byte or each two to four bytes sequence
+represents a character code of a charset specified
+by :charset-list attribute.
+
+If VALUE is `utf-8', the coding system is for handling Unicode
+UTF-8 byte sequence. See also the documentation of the
+attribute :bom.
+
+If VALUE is `utf-16', the coding system is for handling Unicode
+UTF-16 byte sequence. See also the documentation of the
+attributes :bom and :endian.
+
+If VALUE is `iso-2022', the coding system is for handling a byte
+sequence conforming to ISO/IEC 2022. See also the documentation
+of the attributes :charset-list, :flags, and :designation.
+
+If VALUE is `emacs-mule', the coding system is for handling a
+byte sequence which Emacs 20 and 21 used for internal character
+representations.
+
+If VALUE is `shift-jis', the coding system is for handling a byte
+sequence of Shift_JIS format. See also the
+attribute :charset-list.
+
+If VALUE is `ccl', the coding system uses CCL programs to decodes
+and encodes to a byte sequence. The CCL programs must be
+specified by the attributes :ccl-decoder and :ccl-encoder.
+
+If VALUE is `raw-text', the coding system decodes a byte sequence
+as is.
`:eol-type'
and `mac' means Mac-like EOL \(i.e. single CR). If omitted, Emacs
detects the EOL format automatically when decoding.
-`:charset-list'
+`:charset-list' (required if :coding-type is `charset' or `shift-jis')
+
+VALUE must be a list of charsets supported by the coding system.
-VALUE must be a list of charsets supported by the coding system. On
-encoding by the coding system, if a character belongs to multiple
-charsets in the list, a charset that comes earlier in the list is
-selected. If `:coding-type' is `iso-2022', VALUE may be `iso-2022',
-which indicates that the coding system supports all ISO-2022 based
-charsets. If `:coding-type' is `emacs-mule', VALUE may be
-`emacs-mule', which indicates that the coding system supports all
-charsets that have the `:emacs-mule-id' property.
+If `coding-type:' is `charset', on decoding and encoding by the
+coding system, if a character belongs to multiple charsets in the
+list, a charset that comes earlier in the list is selected.
+
+If `:coding-type' is `iso-2022', VALUE may be `iso-2022', which
+indicates that the coding system supports all ISO-2022 based
+charsets.
+
+If `:coding-type' is `shift-jis', VALUE must be a list of three
+to four charsets supported by Shift_JIS encoding scheme. The
+first charset (one dimension) is for code space 0x00..0x7F, the
+second (one dimension) for 0xA1..0xDF, the third (two dimension)
+for 0x8140..0xEFFC, the optional fourth (thw dimension) for
+0xF040..0xFCFC.
+
+If `:coding-type' is `emacs-mule', VALUE may be `emacs-mule',
+which indicates that the coding system supports all charsets that
+have the `:emacs-mule-id' property.
`:ascii-compatible-p'
VALUE must be a list of symbols that control the ISO-2022 converter.
Each must be a member of the list `coding-system-iso-2022-flags'
-\(which see). This attribute has a meaning only when `:coding-type'
+\(which see). This attribute is meaningful only when `:coding-type'
is `iso-2022'.
`:designation'
96 long can be designated to GN. If the first element is a charset,
that charset is initially designated to GN.
-This attribute has a meaning only when `:coding-type' is `iso-2022'.
+This attribute is meaningful only when `:coding-type' is `iso-2022'.
`:bom'
Otherwise, treat them as bytes for a normal character. On encoding,
produce BOM bytes according to the value of `:endian'.
-This attribute has a meaning only when `:coding-type' is `utf-16' or
+This attribute is meaningful only when `:coding-type' is `utf-16' or
`utf-8'.
`:endian'
VALUE must be `big' or `little' specifying big-endian and
little-endian respectively. The default value is `big'.
-This attribute has a meaning only when `:coding-type' is `utf-16'.
+This attribute is meaningful only when `:coding-type' is `utf-16'.
+
+`:ccl-decoder' (required if :coding-type is `ccl')
+
+VALUE is a CCL program name defined by `define-ccl-program'. The
+the CCL program reads a byte sequence and writes a character
+sequence as a decoding result.
+
+`:ccl-encoder' (required if :coding-type is `ccl')
-`:ccl-decoder'
+VALUE is a CCL program name defined by `define-ccl-program'. The
+the CCL program reads a character sequence and writes a byte
+sequence as a encoding result.
-VALUE is a symbol representing the registered CCL program used for
-decoding. This attribute has a meaning only when `:coding-type' is
-`ccl'.
+`:inhibit-null-byte-detection'
-`:ccl-encoder'
+VALUE non-nil means Emacs ignore null bytes on code detection.
+See the variable `inhibit-null-byte-detection'. This attribute
+is meaningful only when `:coding-type' is `undecided'.
-VALUE is a symbol representing the registered CCL program used for
-encoding. This attribute has a meaning only when `:coding-type' is
-`ccl'."
+`:inhibit-iso-escape-detection'
+
+VALUE non-nil means Emacs ignores ISO-2022 escape sequences on
+code detection. See the variable `inhibit-iso-escape-detection'.
+This attribute is meaningful only when `:coding-type' is
+`undecided'.
+
+`:prefer-utf-8'
+
+VALUE non-nil means Emacs prefers UTF-8 on code detection for
+non-ASCII files. This attribute is meaningful only when
+`:coding-type' is `undecided'."
(let* ((common-attrs (mapcar 'list
'(:mnemonic
:coding-type
((eq coding-type 'ccl)
'(:ccl-decoder
:ccl-encoder
- :valids))))))
+ :valids))
+ ((eq coding-type 'undecided)
+ '(:inhibit-null-byte-detection
+ :inhibit-iso-escape-detection
+ :prefer-utf-8))))))
(dolist (slot common-attrs)
(setcdr slot (plist-get props (car slot))))
(and (vectorp eol-type-1) (vectorp eol-type-2)))))))
(defun add-to-coding-system-list (coding-system)
- "Add CODING-SYSTEM to `coding-system-list' while keeping it sorted."
+ "Add CODING-SYSTEM to variable `coding-system-list' while keeping it sorted."
(if (or (null coding-system-list)
(coding-system-lessp coding-system (car coding-system-list)))
(setq coding-system-list (cons coding-system coding-system-list))
(put (intern name) 'coding-system-define-form form)
(setq coding-system-alist (cons (list name) coding-system-alist)))))
-;; This variable is set in these three cases:
+;; This variable is set in these two cases:
;; (1) A file is read by a coding system specified explicitly.
-;; after-insert-file-set-coding sets the car of this value to
-;; coding-system-for-read, and sets the cdr to nil.
-;; (2) A buffer is saved.
-;; After writing, basic-save-buffer-1 sets the car of this value
-;; to last-coding-system-used.
-;; (3) set-buffer-file-coding-system is called.
+;; `after-insert-file-set-coding' sets the car of this value to
+;; `coding-system-for-read', and sets the cdr to nil.
+;; (2) `set-buffer-file-coding-system' is called.
;; The cdr of this value is set to the specified coding system.
-;; This variable is used for decoding in revert-buffer and encoding in
-;; select-safe-coding-system.
+;; This variable is used for decoding in `revert-buffer' and encoding
+;; in `select-safe-coding-system'.
+;;
+;; When saving a buffer, if `buffer-file-coding-system-explicit' is
+;; already non-nil, `basic-save-buffer-1' sets its CAR to the value of
+;; `last-coding-system-used'. (It used to set it unconditionally, but
+;; that seems unnecessary; see Bug#4533.)
+
(defvar buffer-file-coding-system-explicit nil
"The file coding system explicitly specified for the current buffer.
The value is a cons of coding systems for reading (decoding) and
(if (and coding-system buffer-file-coding-system (null force))
(setq coding-system
(merge-coding-systems coding-system buffer-file-coding-system)))
- (when (called-interactively-p 'interactive)
+ (when (and (called-interactively-p 'interactive)
+ (not (memq 'emacs (coding-system-get coding-system
+ :charset-list))))
;; Check whether save would succeed, and jump to the offending char(s)
;; if not.
(let ((css (find-coding-systems-region (point-min) (point-max))))
(if coding-system
(setq default-terminal-coding-system coding-system))
(set-terminal-coding-system-internal coding-system terminal)
- (redraw-frame (selected-frame)))
+ (redraw-frame))
(defvar default-keyboard-coding-system nil
"Default value of the keyboard coding system.
:type '(coding-system :tag "Coding system")
:link '(info-link "(emacs)Terminal Coding")
:link '(info-link "(emacs)Unibyte Mode")
- :set (lambda (symbol value)
+ :set (lambda (_symbol value)
;; Don't load encoded-kb unnecessarily.
(if (or value (boundp 'encoded-kbd-setup-display))
(set-keyboard-coding-system value)
("\\.\\(gz\\|Z\\|bz\\|bz2\\|xz\\|gpg\\)\\'" . no-conversion)
("\\.\\(jpe?g\\|png\\|gif\\|tiff?\\|p[bpgn]m\\)\\'" . no-conversion)
("\\.pdf\\'" . no-conversion)
- ("/#[^/]+#\\'" . emacs-mule)))
+ ("/#[^/]+#\\'" . utf-8-emacs-unix)))
"Alist of filename patterns vs corresponding coding systems.
Each element looks like (REGEXP . CODING-SYSTEM).
A file whose name matches REGEXP is decoded by CODING-SYSTEM on reading.
(head-end (+ head-start (min size 1024)))
(tail-start (+ head-start (max (- size 3072) 0)))
(tail-end (+ head-start size))
- coding-system head-found tail-found pos char-trans)
+ coding-system head-found tail-found char-trans)
;; Try a short cut by searching for the string "coding:"
;; and for "unibyte:" at the head and tail of SIZE bytes.
(setq head-found (or (search-forward "coding:" head-end t)
(re-search-forward
"\\(.*;\\)?[ \t]*unibyte:[ \t]*\\([^ ;]+\\)"
head-end t))
- (display-warning 'mule "`unibyte: t' is obsolete; \
-use \"coding: 'raw-text\" instead." :warning)
+ (display-warning 'mule
+ (format "\"unibyte: t\" (in %s) is obsolete; \
+use \"coding: 'raw-text\" instead."
+ (file-relative-name filename))
+ :warning)
(setq coding-system 'raw-text))
(when (and (not coding-system)
(re-search-forward
(let ((funcs auto-coding-functions)
(coding-system nil))
(while (and funcs (not coding-system))
- (setq coding-system (condition-case e
- (save-excursion
- (goto-char (point-min))
- (funcall (pop funcs) size))
- (error nil))))
+ (setq coding-system (ignore-errors
+ (save-excursion
+ (goto-char (point-min))
+ (funcall (pop funcs) size)))))
(if coding-system
(cons coding-system 'auto-coding-functions)))))